A Multi-Criteria Analysis Technique Using Compromise Programming and the One-Sided Tolerance Interval for the Analysis of Experimentally Planned Tests Evaluating Key Requirements Open Access
Downloadable ContentDownload PDF
This praxis demonstrates through case study, the utility of a multi-criteria decision analysis (MCDA) technique that exploits the features of the one-sided tolerance interval (OSTI) for the analysis of response data resulting from design of experiments (DOE) planned testing. Information distilled from test data is crucial for decision-makers, from the system engineer considering assessing performance, to the program managers and program executives making decisions on whether to proceed. To help reduce the data into information, the systems engineering, and T&E; community use statistical techniques such as descriptive statistics to help explain the test observations. In this research, the use of OSTI, which can be more useful for representing data, was utilized to analyze the output of collected data from DOE structured testing. This combination of DOE for planning and OSTI for interpretation provided a rigorous approach for input into an MCDA process, providing leadership decision quality information for choosing between alternatives. In addition, the findings of this research also demonstrate the utility of using these combinations of techniques to sift through voluminous test results efficiently, providing a novel approach for analyzing data across multiple alternatives, when traditional analysis techniques, such as the descriptive statistics (including the Confidence Interval and mean), obscure information from the untrained eye. Finally, the technique provides a level playing field, a critical feature in today’s acquisition protest culture.